# ArrayDPS: Unsupervised Blind Speech Separation with a Diffusion Prior

arXiv: https://arxiv.org/abs/2505.05657 · HTML: https://mlsanity.com/paper/2505.05657/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in Audio, speech and music, one of 14 directions in Diffusion models.
- Builds on 51 of its 86 references that are in the map.
- First posted on arXiv 8 May 2025.

## Placed in

- Diffusion models / [Audio, speech and music](https://mlsanity.com/diffusion/audio-speech-and-music/)

## Builds on (most cited first, 30 of 51)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Elucidating the Design Space of Diffusion-Based Generative Models](https://mlsanity.com/paper/2206.00364/) (2022)
- [Diffusion Posterior Sampling for General Noisy Inverse Problems](https://mlsanity.com/paper/2209.14687/) (2022)
- [LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speech](https://mlsanity.com/paper/1904.02882/) (2019)
- [SDR - half-baked or well done?](https://mlsanity.com/paper/1811.02508/) (2018)
- [Supervised Speech Separation Based on Deep Learning: An Overview](https://mlsanity.com/paper/1708.07524/) (2017)
- [Deep clustering: Discriminative embeddings for segmentation and separation](https://mlsanity.com/paper/1508.04306/) (2015)
- [Permutation Invariant Training of Deep Models for Speaker-Independent Multi-talker Speech Separation](https://mlsanity.com/paper/1607.00325/) (2016)
- [Parallel Diffusion Models of Operator and Image for Blind Inverse Problems](https://mlsanity.com/paper/2211.10656/) (2022)
- [TF-GridNet: Integrating Full- and Sub-Band Modeling for Speech Separation](https://mlsanity.com/paper/2211.12433/) (2022)
- [Multi-Source Diffusion Models for Simultaneous Music Generation and Separation](https://mlsanity.com/paper/2302.02257/) (2023)
- [Solving Audio Inverse Problems with a Diffusion Model](https://mlsanity.com/paper/2210.15228/) (2022)
- [Into the Wild with AudioScope: Unsupervised Audio-Visual Separation of On-Screen Sounds](https://mlsanity.com/paper/2011.01143/) (2020)
- [Diffusion-based Generative Speech Source Separation](https://mlsanity.com/paper/2210.17327/) (2022)
- [Source Separation with Deep Generative Priors](https://mlsanity.com/paper/2002.07942/) (2020)
- [Fast Diffusion EM: a diffusion model for blind inverse problems with application to deconvolution](https://mlsanity.com/paper/2309.00287/) (2023)
- [End-to-end Microphone Permutation and Number Invariant Multi-channel Speech Separation](https://mlsanity.com/paper/1910.14104/) (2019)
- [AudioScopeV2: Audio-Visual Attention Architectures for Calibrated Open-Domain On-Screen Sound Separation](https://mlsanity.com/paper/2207.10141/) (2022)
- [Blind Audio Bandwidth Extension: A Diffusion-Based Zero-Shot Approach](https://mlsanity.com/paper/2306.01433/) (2023)
- [RemixIT: Continual self-training of speech enhancement models via bootstrapped remixing](https://mlsanity.com/paper/2202.08862/) (2022)
- [Generative Adversarial Source Separation](https://mlsanity.com/paper/1710.10779/) (2017)
- [SpatialNet: Extensively Learning Spatial Information for Multichannel Joint Speech Separation, Denoising and Dereverberation](https://mlsanity.com/paper/2307.16516/) (2023)
- [SMS-WSJ: Database, performance measures, and baseline recipe for multi-channel source separation and recognition](https://mlsanity.com/paper/1910.13934/) (2019)
- [Simultaneous Music Separation and Generation Using Multi-Track Latent Diffusion Models](https://mlsanity.com/paper/2409.12346/) (2024)
- [Unsupervised Deep Clustering for Source Separation: Direct Learning from Mixtures using Spatial Information](https://mlsanity.com/paper/1811.01531/) (2018)
- [On Cross-Corpus Generalization of Deep Learning Based Speech Enhancement](https://mlsanity.com/paper/2002.04027/) (2020)
- [VarArray: Array-Geometry-Agnostic Continuous Speech Separation](https://mlsanity.com/paper/2110.05745/) (2021)
- [Blind Inversion using Latent Diffusion Priors](https://mlsanity.com/paper/2407.01027/) (2024)

## Built on by (most cited first, 7 of 7)

- [StrADiff: A Structured Source-Wise Adaptive Diffusion Framework for Linear and Nonlinear Blind Source Separation](https://mlsanity.com/paper/2604.04973/) (2026)
- [Diffusion-Based Unsupervised Audio-Visual Speech Separation in Noisy Environments with Noise Prior](https://mlsanity.com/paper/2509.14379/) (2025)
- [Ambisonics Encoding of Room Impulse Responses using a Device-Agnostic Diffusion Model](https://mlsanity.com/paper/2608.14097/) (2026)
- [Unsupervised Multi-channel Speech Dereverberation via Diffusion](https://mlsanity.com/paper/2508.02071/) (2025)
- [SSNAPS: Audio-Visual Separation of Speech and Background Noise with Diffusion Inverse Sampling](https://mlsanity.com/paper/2602.01394/) (2026)
- [MeCo: One-Step MeanFlow-based Corrector for Multi-Channel Speech Separation](https://mlsanity.com/paper/2606.09677/) (2026)
- [Music Restoration via Latent Operator Optimization and Diffusion Model Priors](https://mlsanity.com/paper/2608.01972/) (2026)

## Abstract (arXiv)

Blind Speech Separation (BSS) aims to separate multiple speech sources from audio mixtures recorded by a microphone array. The problem is challenging because it is a blind inverse problem, i.e., the microphone array geometry, the room impulse response (RIR), and the speech sources, are all unknown. We propose ArrayDPS to solve the BSS problem in an unsupervised, array-agnostic, and generative manner. The core idea builds on diffusion posterior sampling (DPS), but unlike DPS where the likelihood is tractable, ArrayDPS must approximate the likelihood by formulating a separate optimization problem. The solution to the optimization approximates room acoustics and the relative transfer functions between microphones. These approximations, along with the diffusion priors, iterate through the ArrayDPS sampling process and ultimately yield separated voice sources. We only need a simple single-speaker speech diffusion model as a prior along with the mixtures recorded at the microphones; no microphone array information is necessary. Evaluation results show that ArrayDPS outperforms all baseline unsupervised methods while being comparable to supervised methods in terms of SDR. Audio demos are provided at: https://arraydps.github.io/ArrayDPSDemo/.